Prashanth Rao

fine-grained-sentiment. A comparison and discussion of different NLP methods for 5-class sentiment classification on the SST-5 dataset.

tweet-stance-prediction. Applying NLP transfer learning techniques to predict Tweet stance toward a topic

kuzudb-study. Benchmark study on Kuzu, an embedded graph database, on an artificial social network dataset

db-hub-fastapi. Async bulk data ingestion and querying in various document, graph and vector databases via their Python clients

duckdb-study. Compare DuckDB, Polars and Pandas for generating an artificial dataset of persons and companies

dspy-intro. Code for intro to DSPy blog post

lancedb-study. Comparing LanceDB and Elasticsearch for full-text search and vector search performance

neo4j-python-fastapi. Bulk ingest data into Neo4j using sync or async Python, and expose the data via FastAPI

pydantic-benchmarks. Benchmarks testing the performance of various releases of Pydantic v2 🦀

fine-grained-sentiment-app. A Flask LIME explainer app for fine-grained sentiment classification.

patent-classification. Classify international patents into one of eight categories based on the text of their titles & abstracts using DistilBert & ONNX Runtime

build-with-baml. Example projects using BAML, a DSL that helps generate structured outputs from LLMs

topic-modelling. Comparing the scalability and quality of topic models in Gensim and PySpark

fine-grained-sentiment-app-streamlit. A LIME explainer app for fine-grained sentiment classification, written using Streamlit.

uv-demo. Demo of uv for a streamlined Python package management experience

rag-data-ops. Code for data ops when building RAG applications using LangChain and LlamaIndex

RBIR. Rust

graphdb-case-studies. Case studies showing the analysis of connected data using different graph databases and their Python client libraries

old-hugo-blog. Archived. My blog is now moved to https://github.com/thedataquarry

mteb-validation. Compare different embedding models from MTEB leaderboard

dspy-graph-rag. Experiments with structured outputs and Graph RAG in DSPy

awesome-wasm. 😎 Curated list of awesome things regarding the WebAssembly (wasm) ecosystem.

spectral-line-plots. Plot multiple lines with spectral colors to simultaneously compare similar datasets

sqlmodel. SQL databases in Python, designed for simplicity, compatibility, and robustness.

naacl_transfer_learning_tutorial. Repository of code for the NAACL tutorial on Transfer Learning in NLP

meilisearch-python-sdk. An async and sync Python client for the Meilisearch API

dspy. DSPy: The framework for programming—not prompting—language models

learn. 📚 A curated collection of marimo notebooks for education.

DSRs. A DSPy rewrite to(not port) Rust

langchain. 🦜🔗 Build context-aware reasoning applications

gh-action-test. Test GitHub actions and pre-commit hooks for experimenting with CI/CD and auto-linting workflows.

qdrant-client. Python client for Qdrant vector search engine